-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
No
### Source
source
### TensorFlow version
tf2.13.0
### Custom code
Yes
### OS platform and d…
-
How are we not doing 10000 x 10000 operations in case of Sentence-BERT(for 10000 sentences)? It is understandable that we are using two different BERT architecture for a pair of sentences, but aren't …
-
1. For pairs of sentences that do not display the score , what is the similarity score ?
2. `2015.test.tsv` has 12250 pairs while `2015.train.tsv` has 3000. Is that correct?
-
Hi,
I would like to create my own domain-specific "stsb" datset to further improve performance.
I have a 500 GB domain specific text corpus and want to use / label some of the sentence pairs.
Do …
-
The [Sentences Involving Compositional Knowledge](http://clic.cimec.unitn.it/composes/sick.html) dataset was an older dataset for Natural Language Inference tasks.
From the webpage:
> The SICK …
-
I have been finetuning the paraphrase-multilingual-MiniLM-L12-v2 model on a custom dataset of 500K sentence pairs using a script very similar to [this](https://github.com/UKPLab/sentence-transformers/…
-
GPU：4*RTX 4090 24G
代码是：
```
from FlagEmbedding import BGEM3FlagModel
model = BGEM3FlagModel('BAAI/bge-m3', use_fp16=True)
sentences_1 = ["What is BGE M3?", "Defination of BM25"]
sentences_…
-
Hello!
The (Cached)GISTEmbedLoss classes mask away certain in-batch negatives as they might actually be positives right here: https://github.com/UKPLab/sentence-transformers/blob/f012ab33189d23cef0…
-
Does the sentence pairs need to be tokenised before using the Invitation Model?
-
A100测试
code:
```
import time
from FlagEmbedding import BGEM3FlagModel
model = BGEM3FlagModel('/home/admin/bge-m3', use_fp16=True)
sentences_1 = ["What is BGE M3?", "Defination of BM25"]
…